Using ODE to understand and improve deep learning algoirthm (Neural ODE)(2): Optimization

Using ODE to understand and improve deep learning algoirthm (Neural ODE)(2): Optimization
Including our work at Neurips 2019 and ICML2020
1. Dinghuai Zhang*, Tianyuan Zhang*,Yiping Lu*, Zhanxing Zhu, Bin Dong. "You Only Propagate Once: Painless Adversarial Training Using Maximal Principle." (*equal contribution) 33rd Annual Conference on Neural Information Processing Systems 2019(NeurIPS2019).
2. Yiping Lu*, Chao Ma, Yulong Lu, Jianfeng Lu, Lexing Ying. "A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth" Thirty-seventh International Conference on Machine Learning (ICML), 2020
More information can be found at my homepage: https://web.stanford.edu/~yplu/

Видео Using ODE to understand and improve deep learning algoirthm (Neural ODE)(2): Optimization канала Research 2prime